Xiangyu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiangyu Liu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chunxia Zhao
Section of Health, Nutrition, and Water, Environment and Sanitation, UNICEF China, Beijing, China
1 shared publication - Cui Tao
Department of Artificial Intelligence and Informatics, Mayo Clinic, Jacksonville, FL 32224, USA
1 shared publication - Cuihong Zhang
Department of Child, Adolescent and Women’s Health, School of Public Health, Peking University, Beijing, China
1 shared publication - Hsing-Yi Song
University of Texas School of Biomedical Informatics, 7000 Fannin St Suite 600, Houston, TX, 77030, USA
1 shared publication - Jingcheng Du
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
1 shared publication - Jingxu Zhang
Department of Maternal and Child Health, School of Public Health, Peking University, Beijing, PR China
1 shared publication
Latest Publications
- Open Access
- 8 December 2017
- Published by Springer Nature in International Journal for Equity in Health
- Vol. 16 (1) , 1-10
Inequality in early childhood neurodevelopment in six poor rural counties of China: a decomposition analysis
Previous studies about inequality in children’s health focused more on physical health than the neurodevelopment. In this study, we aimed to evaluate the inequality in early childhood neurodevelopment in poor rural China and explore the contributions of socioeconomic factors to the inequality. Information of 2120 children aged 0 to 35 months and their households in six poor rural counties of China was collected during July – September, 2013. Age and Stages Questionnaire-Chinese version, concentration index and decomposition analysis were used to assess the neurodevelopment of early childhood, measure its inequality and evaluate the contributions of socioeconomic factors to the inequality, respectively. The prevalence of suspected developmental delay in children under 35 months of age in six poor rural counties of China was nearly 40%, with the concentration index of −0.0877. Household economic status, caregivers’ depressive symptoms, learning material and family support for learning were significantly associated with children’s suspected developmental delay, and explained 34.1, 14.1, 8.9 and 7.0% of the inequality in early childhood neurodevelopment, respectively. The early childhood neurodevelopment in the surveyed area is poor and unfair. Factors including household economic status, caregivers’ depressive symptoms, learning material and family support for learning are significantly associated with children’s suspected developmental delay and early developmental inequality. The results highlight the urgent need of monitoring child neurodevelopment in poor rural areas. Interventions targeting the caregivers’ depressive symptoms, providing learning material and developmental appropriate stimulating activities may help improve early childhood neurodevelopment and reduce its inequality.
- 8 December 2017
- Published by Springer Nature in International Journal for Equity in Health
- Vol. 16 (1) , 1-10
Open AccessInequality in early childhood neurodevelopment in six poor rural counties of China: a decomposition analysis
Previous studies about inequality in children’s health focused more on physical health than the neurodevelopment. In this study, we aimed to evaluate the inequality in early childhood neurodevelopment in poor rural China and explore the contributions of socioeconomic factors to the inequality. Information of 2120 children aged 0 to 35 months and their households in six poor rural counties of China was collected during July – September, 2013. Age and Stages Questionnaire-Chinese version, concentration index and decomposition analysis were used to assess the neurodevelopment of early childhood, measure its inequality and evaluate the contributions of socioeconomic factors to the inequality, respectively. The prevalence of suspected developmental delay in children under 35 months of age in six poor rural counties of China was nearly 40%, with the concentration index of −0.0877. Household economic status, caregivers’ depressive symptoms, learning material and family support for learning were significantly associated with children’s suspected developmental delay, and explained 34.1, 14.1, 8.9 and 7.0% of the inequality in early childhood neurodevelopment, respectively. The early childhood neurodevelopment in the surveyed area is poor and unfair. Factors including household economic status, caregivers’ depressive symptoms, learning material and family support for learning are significantly associated with children’s suspected developmental delay and early developmental inequality. The results highlight the urgent need of monitoring child neurodevelopment in poor rural areas. Interventions targeting the caregivers’ depressive symptoms, providing learning material and developmental appropriate stimulating activities may help improve early childhood neurodevelopment and reduce its inequality.
- Open Access
- 3 March 2017
- Published by Springer Nature in Journal of Biomedical Semantics
- Vol. 8 (1) , 1-7
Optimization on machine learning based approaches for sentiment analysis on HPV vaccines related tweets
Analysing public opinions on HPV vaccines on social media using machine learning based approaches will help us understand the reasons behind the low vaccine coverage and come up with corresponding strategies to improve vaccine uptake. To propose a machine learning system that is able to extract comprehensive public sentiment on HPV vaccines on Twitter with satisfying performance. We collected and manually annotated 6,000 HPV vaccines related tweets as a gold standard. SVM model was chosen and a hierarchical classification method was proposed and evaluated. Additional feature sets evaluation and model parameters optimization was done to maximize the machine learning model performance. A hierarchical classification scheme that contains 10 categories was built to access public opinions toward HPV vaccines comprehensively. A 6,000 annotated tweets gold corpus with Kappa annotation agreement at 0.851 was created and made public available. The hierarchical classification model with optimized feature sets and model parameters has increased the micro-averaging and macro-averaging F score from 0.6732 and 0.3967 to 0.7442 and 0.5883 respectively, compared with baseline model. Our work provides a systematical way to improve the machine learning model performance on the highly unbalanced HPV vaccines related tweets corpus. Our system can be further applied on a large tweets corpus to extract large-scale public opinion towards HPV vaccines.
- 3 March 2017
- Published by Springer Nature in Journal of Biomedical Semantics
- Vol. 8 (1) , 1-7
Open AccessOptimization on machine learning based approaches for sentiment analysis on HPV vaccines related tweets
Analysing public opinions on HPV vaccines on social media using machine learning based approaches will help us understand the reasons behind the low vaccine coverage and come up with corresponding strategies to improve vaccine uptake. To propose a machine learning system that is able to extract comprehensive public sentiment on HPV vaccines on Twitter with satisfying performance. We collected and manually annotated 6,000 HPV vaccines related tweets as a gold standard. SVM model was chosen and a hierarchical classification method was proposed and evaluated. Additional feature sets evaluation and model parameters optimization was done to maximize the machine learning model performance. A hierarchical classification scheme that contains 10 categories was built to access public opinions toward HPV vaccines comprehensively. A 6,000 annotated tweets gold corpus with Kappa annotation agreement at 0.851 was created and made public available. The hierarchical classification model with optimized feature sets and model parameters has increased the micro-averaging and macro-averaging F score from 0.6732 and 0.3967 to 0.7442 and 0.5883 respectively, compared with baseline model. Our work provides a systematical way to improve the machine learning model performance on the highly unbalanced HPV vaccines related tweets corpus. Our system can be further applied on a large tweets corpus to extract large-scale public opinion towards HPV vaccines.